Igor Jurisica*
Schroeder Arthritis Institute and Data Science Discovery Centre for Chronic Diseases Krembil Research Institute University Health Network; University of Toronto; Mohamed bin Zayed University of Artificial Intelligence, Slovak Academy of Sciences
juris [at] ai.utoronto.ca
Abstract
Data-driven discoveries are becoming transformative. AI and integrative computational biology help improving treatment of complex diseases. However, clinical applications require deeper understanding of the system and its underlying processes. Systematic integration of multi-omics datasets with rich biological networks does help to build explainable models, which in turn address questions of trust, fairness, empathy, and governance. Without proper management of such complex biological and clinical data, AI algorithms cannot be effectively trained, validated and successfully applied.
Despite challenges, there are many opportunities in precision medicine using AI, big data analytics and integrative computational biology workflows. From systematic data curation and analysis to improved biomarkers, drug mechanism of action, and patient selection, such analyses enable patient-centric medicine.
Mapping diverse clinical, multi-omic and multi-spectral data to diverse biological networks, further annotating with ontologies and atlases requires spectrum of algorithms from data mining, machine learning, graph theory and advanced visualization to aid analysis, model building and interpretation. Intertwining computational prediction and modeling with biological experiments and preclinical studies will lead to more useful findings faster and more economically.
Keywords: Data science, AI, network biology
Acknowledgement: This work was supported in part by funding from Natural Sciences Research Council (NSERC RGPIN-2024-04314), CIHR (#519474), Canada Foundation for Innovation (CFI #225404, #30865), Ontario Research Fund (RDI #34876, RE010-020), Krembil Foundation and Ian Lawson van Toch Fund.